Lecturer: Alex Bouchard
Date: Oct 1
- Isabelle Guyon, Andre Elisseeff.
An Introduction to Variable and Feature Selection.
Provides a general overview of feature selection.
- Tim Hesterberg, Nam Hee Choi, Lukas Meier, and Chris Fraley. Least angle and L1 penalized regression: A review. Statist. Surv. 2008.
- Galen Andrew , Jianfeng Gao. Scalable training of L1-regularized log-linear models. ICML 2007. Open source implementation here (see edu.berkeley.nlp.math.OW_LBFGSMinimizer).
- Isabelle Guyon, Constantin Aliferis, Andre Elisseeff. Causal Feature Selection. 2007.
- Jianfeng Gao, Galen Andrew, Mark Johnson, Kristina Toutanova.
Comparative Study of Parameter Estimation Methods for
Statistical Natural Language Processing. ACL 2007.
Compares many different methods including ordinary logistic regression,
logistic regression with L1 regularization (to get sparsity in features),
and boosting (another way to get sparsity).
- Bradley Efron, Trevor Hastie, Iain Johnstone and Robert Tibshirani.
Least Angle Regression. 2004.
- Robert Tibshirani.
Regression Shrinkage and Selection via the Lasso.
- Ron Kohavi , George H. John. Wrappers for Feature Subset Selection. 1996.
Case studies and applications
Papers not directly related to feature selection but referenced in the lecture